In this example, we want to build and train a deep convolutional variational autoencoder based on the Olivetti faces dataset. The structure is very similar to the one employed in our first example. The encoder has the following layers:
- 2D convolution with 16 (3 × 3) filters, (2 × 2) strides, ReLU activation, and the same padding
- 2D convolution with 32 (3 × 3) filters, (1 × 1) strides, ReLU activation, and the same padding
- 2D convolution with 64 (3 × 3) filters, (1 × 1) strides, ReLU activation, and the same padding
- 2D convolution with 128 (3 × 3) filters, (1 × 1) strides, ReLU activation, and the same padding
The decoder has the following transpose convolutions:
- 2D transpose convolution ...
